A medical volume reconstruction method using tetrahedral meshes and level set

A volumetric medical image reconstruction method using tetrahedral meshes and level set is proposed whereby non-discrete models are reconstructed from grid based volume By this method, the discrete volumetric medical image is first segmented by coupled level sets driven by a pathologically modelled energy functional. The segmentation will divide the volume into pathologically meaningful regions. The volume will then be changed from regular grid data to a tetrahedral mesh. To reduce the volume of the mesh, a hybrid sculpting scheme is proposed to reduce the amount of redundancy and noise while preserving the important features. The hybrid sculpting scheme consists of internal sculpting and surface sculpting, which is able to provide multiple levels of detail through each iteration of sculpting thus enabling efficient reconstruction and visualization of the data. Initial results show that the proposed framework is able to maintain important features with reduced data volume while changing the data representation from regular grids to a tetrahedral mesh.